| { | |
| "architectures": [ | |
| "ViTForImageClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "encoder_stride": 16, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "East Asian", | |
| "1": "Indian", | |
| "2": "Black", | |
| "3": "White", | |
| "4": "Middle Eastern", | |
| "5": "Latino_Hispanic", | |
| "6": "Southeast Asian" | |
| }, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "Black": 2, | |
| "East Asian": 0, | |
| "Indian": 1, | |
| "Latino_Hispanic": 5, | |
| "Middle Eastern": 4, | |
| "Southeast Asian": 6, | |
| "White": 3 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "model_type": "vit", | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 16, | |
| "pooler_act": "tanh", | |
| "pooler_output_size": 768, | |
| "problem_type": "single_label_classification", | |
| "qkv_bias": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.4" | |
| } | |